Accelerated gradient methods for geodesically convex optimization: Tractable algorithms and convergence analysis

J Kim, I Yang - International Conference on Machine …, 2022 - proceedings.mlr.press
We propose computationally tractable accelerated first-order methods for Riemannian
optimization, extending the Nesterov accelerated gradient (NAG) method. For both …

Lie group forced variational integrator networks for learning and control of robot systems

V Duruisseaux, TP Duong, M Leok… - … for Dynamics and …, 2023 - proceedings.mlr.press
Incorporating prior knowledge of physics laws and structural properties of dynamical
systems into the design of deep learning architectures has proven to be a powerful …

A variational formulation of accelerated optimization on Riemannian manifolds

V Duruisseaux, M Leok - SIAM Journal on Mathematics of Data Science, 2022 - SIAM
It was shown recently by W. Su, S. Boyd, and E. Candes, J. Mach. Learn. Res., 17 (2016),
pp. 1--43 that Nesterov's accelerated gradient method for minimizing a smooth convex …

Adaptive Hamiltonian variational integrators and applications to symplectic accelerated optimization

V Duruisseaux, J Schmitt, M Leok - SIAM Journal on Scientific Computing, 2021 - SIAM
It is well known that symplectic integrators lose their near energy preservation properties
when variable time-steps are used. The most common approach to combining adaptive time …

Generalizing adam to manifolds for efficiently training transformers

B Brantner - arXiv preprint arXiv:2305.16901, 2023 - arxiv.org
One of the primary reasons behind the success of neural networks has been the emergence
of an array of new, highly-successful optimizers, perhaps most importantly the Adam …

Practical perspectives on symplectic accelerated optimization

V Duruisseaux, M Leok - Optimization Methods and Software, 2023 - Taylor & Francis
Geometric numerical integration has recently been exploited to design symplectic
accelerated optimization algorithms by simulating the Bregman Lagrangian and Hamiltonian …

Time-adaptive Lagrangian variational integrators for accelerated optimization on manifolds

V Duruisseaux, M Leok - arXiv preprint arXiv:2201.03774, 2022 - arxiv.org
A variational framework for accelerated optimization was recently introduced on normed
vector spaces and Riemannian manifolds in Wibisono et al.(2016) and Duruisseaux and …

Projected Neural Differential Equations for Learning Constrained Dynamics

A White, A Büttner, M Gelbrecht, V Duruisseaux… - arXiv preprint arXiv …, 2024 - arxiv.org
Neural differential equations offer a powerful approach for learning dynamics from data.
However, they do not impose known constraints that should be obeyed by the learned …

A Symplectic Analysis of Alternating Mirror Descent

J Katona, X Wang, A Wibisono - arXiv preprint arXiv:2405.03472, 2024 - arxiv.org
Motivated by understanding the behavior of the Alternating Mirror Descent (AMD) algorithm
for bilinear zero-sum games, we study the discretization of continuous-time Hamiltonian flow …

Nesterov acceleration for Riemannian optimization

J Kim, I Yang - arXiv preprint arXiv:2202.02036, 2022 - arxiv.org
In this paper, we generalize the Nesterov accelerated gradient (NAG) method to solve
Riemannian optimization problems in a computationally tractable manner. The iteration …